1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
|
/*-
* Copyright (c) 1993, David Greenman
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/vnode.h>
#include <sys/proc.h>
#include <sys/sbuf.h>
#include <sys/systm.h>
#include <sys/sysproto.h>
#include <sys/exec.h>
#include <sys/imgact.h>
#include <sys/kernel.h>
#if BYTE_ORDER == LITTLE_ENDIAN
#define SHELLMAGIC 0x2123 /* #! */
#else
#define SHELLMAGIC 0x2321
#endif
/*
* At the time of this writing, MAXSHELLCMDLEN == PAGE_SIZE. This is
* significant because the caller has only mapped in one page of the
* file we're reading. This code should be changed to know how to
* read in the second page, but I'm not doing that just yet...
*/
#if MAXSHELLCMDLEN > PAGE_SIZE
#error "MAXSHELLCMDLEN is larger than a single page!"
#endif
/**
* Shell interpreter image activator. An interpreter name beginning at
* imgp->args->begin_argv is the minimal successful exit requirement.
*
* If the given file is a shell-script, then the first line will start
* with the two characters `#!' (aka SHELLMAGIC), followed by the name
* of the shell-interpreter to run, followed by zero or more tokens.
*
* The interpreter is then started up such that it will see:
* arg[0] -> The name of interpreter as specified after `#!' in the
* first line of the script. The interpreter name must
* not be longer than MAXSHELLCMDLEN bytes.
* arg[1] -> *If* there are any additional tokens on the first line,
* then we add a new arg[1], which is a copy of the rest of
* that line. The copy starts at the first token after the
* interpreter name. We leave it to the interpreter to
* parse the tokens in that value.
* arg[x] -> the full pathname of the script. This will either be
* arg[2] or arg[1], depending on whether or not tokens
* were found after the interpreter name.
* arg[x+1] -> all the arguments that were specified on the original
* command line.
*
* This processing is described in the execve(2) man page.
*/
/*
* HISTORICAL NOTE: From 1993 to mid-2005, FreeBSD parsed out the tokens as
* found on the first line of the script, and setup each token as a separate
* value in arg[]. This extra processing did not match the behavior of other
* OS's, and caused a few subtle problems. For one, it meant the kernel was
* deciding how those values should be parsed (wrt characters for quoting or
* comments, etc), while the interpreter might have other rules for parsing.
* It also meant the interpreter had no way of knowing which arguments came
* from the first line of the shell script, and which arguments were specified
* by the user on the command line. That extra processing was dropped in the
* 6.x branch on May 28, 2005 (matching __FreeBSD_version 600029).
*/
int
exec_shell_imgact(imgp)
struct image_params *imgp;
{
const char *image_header = imgp->image_header;
const char *ihp, *interpb, *interpe, *maxp, *optb, *opte, *fname;
int error, offset;
size_t length, clength;
struct vattr vattr;
struct sbuf *sname;
/* a shell script? */
if (((const short *) image_header)[0] != SHELLMAGIC)
return(-1);
/*
* Don't allow a shell script to be the shell for a shell
* script. :-)
*/
if (imgp->interpreted)
return(ENOEXEC);
imgp->interpreted = 1;
/*
* At this point we have the first page of the file mapped.
* However, we don't know how far into the page the contents are
* valid -- the actual file might be much shorter than the page.
* So find out the file size.
*/
error = VOP_GETATTR(imgp->vp, &vattr, imgp->proc->p_ucred);
if (error)
return (error);
/*
* Copy shell name and arguments from image_header into a string
* buffer. Remember that the caller has mapped only the
* first page of the file into memory.
*/
clength = (vattr.va_size > PAGE_SIZE) ? PAGE_SIZE : vattr.va_size;
maxp = &image_header[clength];
ihp = &image_header[2];
/*
* Find the beginning and end of the interpreter_name. If the
* line does not include any interpreter, or if the name which
* was found is too long, we bail out.
*/
while (ihp < maxp && ((*ihp == ' ') || (*ihp == '\t')))
ihp++;
interpb = ihp;
while (ihp < maxp && ((*ihp != ' ') && (*ihp != '\t') && (*ihp != '\n')
&& (*ihp != '\0')))
ihp++;
interpe = ihp;
if (interpb == interpe)
return (ENOEXEC);
if ((interpe - interpb) >= MAXSHELLCMDLEN)
return (ENAMETOOLONG);
/*
* Find the beginning of the options (if any), and the end-of-line.
* Then trim the trailing blanks off the value. Note that some
* other operating systems do *not* trim the trailing whitespace...
*/
while (ihp < maxp && ((*ihp == ' ') || (*ihp == '\t')))
ihp++;
optb = ihp;
while (ihp < maxp && ((*ihp != '\n') && (*ihp != '\0')))
ihp++;
opte = ihp;
while (--ihp > optb && ((*ihp == ' ') || (*ihp == '\t')))
opte = ihp;
if (imgp->args->fname != NULL) {
fname = imgp->args->fname;
sname = NULL;
} else {
sname = sbuf_new_auto();
sbuf_printf(sname, "/dev/fd/%d", imgp->args->fd);
sbuf_finish(sname);
fname = sbuf_data(sname);
}
/*
* We need to "pop" (remove) the present value of arg[0], and "push"
* either two or three new values in the arg[] list. To do this,
* we first shift all the other values in the `begin_argv' area to
* provide the exact amount of room for the values added. Set up
* `offset' as the number of bytes to be added to the `begin_argv'
* area, and 'length' as the number of bytes being removed.
*/
offset = interpe - interpb + 1; /* interpreter */
if (opte > optb) /* options (if any) */
offset += opte - optb + 1;
offset += strlen(fname) + 1; /* fname of script */
length = (imgp->args->argc == 0) ? 0 :
strlen(imgp->args->begin_argv) + 1; /* bytes to delete */
if (offset - length > imgp->args->stringspace) {
if (sname != NULL)
sbuf_delete(sname);
return (E2BIG);
}
bcopy(imgp->args->begin_argv + length, imgp->args->begin_argv + offset,
imgp->args->endp - (imgp->args->begin_argv + length));
offset -= length; /* calculate actual adjustment */
imgp->args->begin_envv += offset;
imgp->args->endp += offset;
imgp->args->stringspace -= offset;
/*
* If there was no arg[0] when we started, then the interpreter_name
* is adding an argument (instead of replacing the arg[0] we started
* with). And we're always adding an argument when we include the
* full pathname of the original script.
*/
if (imgp->args->argc == 0)
imgp->args->argc = 1;
imgp->args->argc++;
/*
* The original arg[] list has been shifted appropriately. Copy in
* the interpreter name and options-string.
*/
length = interpe - interpb;
bcopy(interpb, imgp->args->buf, length);
*(imgp->args->buf + length) = '\0';
offset = length + 1;
if (opte > optb) {
length = opte - optb;
bcopy(optb, imgp->args->buf + offset, length);
*(imgp->args->buf + offset + length) = '\0';
offset += length + 1;
imgp->args->argc++;
}
/*
* Finally, add the filename onto the end for the interpreter to
* use and copy the interpreter's name to imgp->interpreter_name
* for exec to use.
*/
error = copystr(fname, imgp->args->buf + offset, imgp->args->stringspace,
&length);
if (error == 0)
error = copystr(imgp->args->begin_argv, imgp->interpreter_name,
MAXSHELLCMDLEN, &length);
if (sname != NULL)
sbuf_delete(sname);
return (error);
}
/*
* Tell kern_execve.c about it, with a little help from the linker.
*/
static struct execsw shell_execsw = { exec_shell_imgact, "#!" };
EXEC_SET(shell, shell_execsw);
|